Pith. sign in

← back to paper

Review history

arxiv: 2607.23870 · 2 revisions

MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents

  1. 2026-07-30 CONDITIONAL HIGH v1.2.0-grok45-kimik3 novelty 6.0
    85031 ms 32242 in 4165 out 2026-07-30T13:45:24.021243+00:00
  2. 2026-07-30 CONDITIONAL LOW v1.2.0-grok45-kimik3 novelty 5.0
    56235 ms 6218 in 2836 out 2026-07-30T10:06:13.551120+00:00